• 한국해안해양공학회지
• /
• 제18권4호
• /
• pp.360-371
• /
• 2006

천해역의 파랑을 추산하기 위한 포물형 근사식에 대해 기존 모형을 도출할 수 있는 일반화된 모형을 제시하고 이를 수정 완경사 파랑식에 대한 포물형 근사식으로 확장하였다. 제시한 수치모형을 Berkhoff et al.(1982)의 수리모형 실험과 비교하였으며 이 경우에는 기존 포물형 근사모형과 수정 포물형 근사모형의 결과가 거의 같으며 수리실험 결과와 아주 잘 일치하는 것으로 나타났다. 따라서 계산이 빠르고 안정성이 높은 기존 포물형 근사식은 천해역의 파랑 추산에 유용한 도구라 판단된다.

• 한국콘텐츠학회논문지
• /
• 제3권1호
• /
• pp.31-38
• /
• 2003

본 논문에서는 탐지 모델을 자동 생성하여 인력, 시간에서의 효율성과 오탐율을 향상시키는 학습을 통한 탐지 모델 생성 시스템을 제안한다. 제안된 탐지 모델 생성 시스템은 agent 시스템과 manager 시스템으로 구성되고 agent 시스템은 탐지 모델 데이터베이스를 기반으로 센서의 역활을 수행하고 manager 시스템에서는 탐지 모델 생성과 모델 분산의 역할을 수행한다. 모델 생성은 유전적 알고리즘에 의해 기존의 정형화된 포맷의 탐지 모델을 학습시켜 모델을 생성하고 새로운 탐지 모델로 적용할 수 있다. 실험 결과에 따라 제안된 데이터 마이닝 기반의 탐지 모델 생성 시스템은 기존의 침입 탐지 시스템보다 효율적으로 침입을 탐지하였다. 구현된 시스템으로 인하여 새로운 유형의 침입 시 탐지 모델 생성과, False-Positive율의 감소를 가져와 기존 침입 탐지 시스템의 성능을 개선하여 탐지모델 생성 시스템을 제안한다.

• Nuclear Engineering and Technology
• /
• 제28권3호
• /
• pp.299-310
• /
• 1996

A two-step approach has been used to obtain a new criterion for the onset of slug formation : (1) In the first step, a more general expression than the existing models for the onset of slug flow criterion has been derived from the analysis of singular points and neutral stability conditions of the transient one-dimensional two-phase flow equations of two-fluid model. (2) In the second step, introducing simplifications and incorporating a parameter into the general expression obtained in the first step to satisfy a number of physical conditions a priori specified, a new simple criterion for the onset of slug flow has been derived. Comparisons of the present model with existing models and experimental data show that the present model agrees very closely with Taitel & Dukler's model and experimental data in horizontal pipes. In an inclined pipe ($\theta$ =50$^{\circ}$), however, the difference between the predictions of the present model and those of existing models is appreciably large and the present model gives the best agreement with Ohnuki et al.'s data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.1080-1099
• /
• 2019

A better tradeoff between robustness and invisibility will be realized by using the just noticeable (JND) model into the quantization-based watermarking scheme. The JND model is usually used to describe the perception characteristics of human visual systems (HVS). According to the research of cognitive science, HVS can adaptively extract the structure features of an image. However, the existing JND models in the watermarking scheme do not consider the structure features. Therefore, a novel JND model is proposed, which includes three aspects: contrast sensitivity function, luminance adaptation, and contrast masking (CM). In this model, the CM effect is modeled by analyzing the direction features and texture complexity, which meets the human visual perception characteristics and matches well with the spread transform dither modulation (STDM) watermarking framework by employing a new method to measure edge intensity. Compared with the other existing JND models, the proposed JND model based on structural regularity is more efficient and applicable in the STDM watermarking scheme. In terms of the experimental results, the proposed scheme performs better than the other watermarking scheme based on the existing JND models.

• Computers and Concrete
• /
• 제32권3호
• /
• pp.313-326
• /
• 2023

The seismic safety of the shear wall structure can be assessed through seismic fragility analysis, which requires high computational costs in estimating seismic demands. Accordingly, machine learning methods have been applied to such fragility analyses in recent years to reduce the numerical analysis cost, but it still remains a challenging task. Therefore, this study uses the ensemble machine learning method to present an improved framework for developing a more accurate seismic demand model than the existing ones. To this end, a rank-based selection method that enables determining an excellent model among several single machine learning models is presented. In addition, an index that can evaluate the degree of overfitting/underfitting of each model for the selection of an excellent single model is suggested. Furthermore, based on the selected single machine learning model, we propose a method to derive a more accurate ensemble model based on the bagging method. As a result, the seismic demand model for which the proposed framework is applied shows about 3-17% better prediction performance than the existing single machine learning models. Finally, the seismic fragility obtained from the proposed framework shows better accuracy than the existing fragility methods.

• 한국공간구조학회논문집
• /
• 제22권4호
• /
• pp.89-98
• /
• 2022

The recent earthquake in Korea caused a lot of damage to reinforced concrete (RC) columns with non-seismic details. The nonlinear analysis enables predicting the hysteresis behavior of RC columns under earthquakes, but the analytical model used for the columns must be accurate and practical. This paper studied the nonlinear analysis models built into a commercial structural analysis program for the existing RC columns. The load-displacement relationships, maximum strength, initial stiffness, and energy dissipation predicted by the three analysis models were compared and analyzed. The results were similar to those tested in the order of the fiber, Pivot, and Takeda models, whereas the fiber model took the most time to build. For columns subjected to axial load, the Pivot model could predict the behavior at a similar level to that of the fiber model. Based on the above, it is expected that the Pivot model can be applied most practically for existing RC columns.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제27권4호
• /
• pp.311-323
• /
• 2023

This paper introduces the industrial problem, the solution, and the results of the research conducted with Define Inc. The client company wanted to improve the performance of an object detection model on the floor plan dataset. To solve the problem, we analyzed the operational principles, advantages, and disadvantages of the existing object detection model, identified the characteristics of the floor plan dataset, and proposed to use of YOLO v5 as an appropriate object detection model for training the dataset. We compared the performance of the existing model and the proposed model using mAP@60, and verified the object detection results with real test data, and found that the performance increase of mAP@60 was 0.08 higher with a 25% shorter inference time. We also found that the training time of the proposed YOLO v5 was 71% shorter than the existing model because it has a simpler structure. In this paper, we have shown that the object detection model for the floor plan dataset can achieve better performance while reducing the training time. We expect that it will be useful for solving other industrial problems related to object detection in the future. We also believe that this result can be extended to study object recognition in 3D floor plan dataset.

• 정보처리학회논문지D
• /
• 제12D권2호
• /
• pp.211-218
• /
• 2005

본 연구는 금융기관에서의 고객신용평가를 위한 최적의 데이터마이닝 모형을 제안한다. 이를 위해 할부금융시장에서의 고객정보 및 할부진행 과정에 대한 세부 내역을 바탕으로 다계층 퍼셉트론(Multi-Layered Perceptrons:MLP)과 다변량 판별분석(Multivariate Discrimination Analysis : MDA), 그리고 의사결정나무(Decision Tree)를 적용하여 각각의 개별모형을 도출하고 이론 유전자 알고리즘을 이용하여 통합한 최종 모형을 구해 그 결과론 각 단일모형과 비교${\cdot}$분석하였다. 그 견과 유전자 알고리즘을 통해 결합한 통합모형의 성능이 가장 우수한 것으로 나타났다. 이에 본 연구는 기존에 진행되었던 개변모형에 대한 검증은 물론, 단순히 여러 개의 모형을 비교${\cdot}$분석하여 우월한 모형을 평가하는 기존 방법론 상의 한계를 극복하기 위해 각각의 개별모형을 유전자 알고리즘을 통해 통합모형으로 구축하는 하나의 방법론을 제시하였다는데 그 의의가 있다.

• 한국군사과학기술학회지
• /
• 제13권2호
• /
• pp.258-267
• /
• 2010

The necessity of the new system development arises in both defence and commercial systems industry either when a breakthrough in technology needs to be realized in the form of a brand-new system or when the existing product already in operation needs to be upgraded to satisfy the increasing stakeholder's requirements. In the latter case, it is not rare that specific system technical specifications on the existing products are not available. The purpose of this study is to investigate how to handle the difficulty when an upgraded system is required to be developed based on the existing product whose detailed technical specifications cannot be obtained. A step-by-step process is described based on the reverse engineering of the existing product. As a result, a logical system model is obtained for the product. The process developed is further enhanced and evaluated by the computer-aided system engineering tool. The resulting logical system model should be helpful in the next phase of the new product development.

• 한국해안해양공학회지
• /
• 제8권2호
• /
• pp.161-173
• /
• 1996

전지구 해양의 M$_2$조석 특성을 파악하기 위해 1$^{\circ}$및 1/3$^{\circ}$의 분해능을 갖는 2차원 수치모형을 수립하였다. 특히 수립된 1/3$^{\circ}$수치모형은 현재까지 수행된 전지구 해양 수치모형 중 가장 분해능이 높은 모형으로 기존 수치모형에서 낮은 분해능으로 인하여 평가하지 못하였던 천해역 및 육붕해에서의 조석현상을 평가하였다. 작성된 조석도는 기존의 수치모형 및 위성 고도계 자료로부터 작성된 조석도와 심해의 일부 지역에서 관측된 조화상수와 상호 비교하였다. 계산결과는 1$^{\circ}$모형에 비하여 1/3$^{\circ}$모형에서 향상되었고 1/3$^{\circ}$수치모형의 계산 결과는 국지적 수치모형 운영시 외해 개방 경계조건으로 이용될 수 있음을 제시하였다.